Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-xqmj-j6mv-4862

LiteLLM: Server-Side Template Injection in /prompts/test endpoint

CVSS 8.6 HighEPSS 0.0037 · 31st percentile

Published by the GitHub Advisory Database at 24 Apr 2026, 16:02 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
litellmPyPI>=1.80.5, <1.83.71.83.7
Identifiers
GHSA-xqmj-j6mv-4862 · CVE-2026-42203 · PYSEC-2026-2602
Weakness (CWE)
CWE-94 · CWE-1336
Tags
Published
24 Apr 2026
Updated
10 Sept 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

LiteLLM versions >=1.80.5 and <1.83.7 are affected by a server-side template injection in the POST /prompts/test endpoint, which renders user-supplied prompt templates without sandboxing. Any user with a valid proxy API key can reach it and potentially run arbitrary code in the proxy process, exposing environment secrets and possibly commands on the host. Upgrade to 1.83.7 or later; until then, block that endpoint at your reverse proxy or API gateway and rotate keys that should not access prompt routes.

Written 5 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
8.6 High 4.0 CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0037, the 31st percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:34 UTC First seen by agentprime
  2. 31 Oct 2026, 14:34 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.